© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84787
    Prev
    Next
    INDEX
    Explanations

    names and weibo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     意思
    -2.55
     have
    -2.52
    na
    -2.48
    ㌧
    -2.45
    也就是说
    -2.38
     Gegenstände
    -2.36
    除此
    -2.28
     ages
    -2.25
     价格
    -2.25
     about
    -2.20
    POSITIVE LOGITS
    {
    3.19
    他
    2.39
     Université
    2.38
    すみません
    2.36
     что
    2.36
     It
    2.36
    它
    2.34
     &
    2.33
    薷
    2.31
    It
    2.30
    Activations Density 0.007%

    No Known Activations